From f47944cc2dba3c7e6f753b81e9f713f4d12bdd5a Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Wed, 16 Oct 2013 17:37:49 +0300 Subject: IPoIB: Fix deadlock between dev_change_flags() and __ipoib_dev_flush() When ipoib interface is going down it takes all of its children with it, under mutex. For each child, dev_change_flags() is called. That function calls ipoib_stop() via the ndo, and causes flush of the workqueue. Sometimes in the workqueue an __ipoib_dev_flush work() is waiting and when invoked tries to get the same mutex, which leads to a deadlock, as seen below. The solution is to switch to rw-sem instead of mutex. The deadlock: [11028.165303] [] ? vgacon_scroll+0x107/0x2e0 [11028.171844] [] schedule_timeout+0x215/0x2e0 [11028.178465] [] ? perf_event_task_sched_out+0x33/0x80 [11028.185962] [] wait_for_common+0x123/0x180 [11028.192491] [] ? default_wake_function+0x0/0x20 [11028.199504] [] wait_for_completion+0x1d/0x20 [11028.206224] [] flush_cpu_workqueue+0x61/0x90 [11028.212948] [] ? wq_barrier_func+0x0/0x20 [11028.219375] [] flush_workqueue+0x54/0x80 [11028.225712] [] ipoib_mcast_stop_thread+0x66/0x90 [ib_ipoib] [11028.233988] [] ipoib_ib_dev_down+0x6a/0x100 [ib_ipoib] [11028.241678] [] ipoib_stop+0x8a/0x140 [ib_ipoib] [11028.248692] [] dev_close+0x71/0xc0 [11028.254447] [] dev_change_flags+0xa1/0x1d0 [11028.261062] [] ipoib_stop+0x10b/0x140 [ib_ipoib] [11028.268172] [] dev_close+0x71/0xc0 [11028.273922] [] dev_change_flags+0xa1/0x1d0 [11028.280452] [] devinet_ioctl+0x5eb/0x6a0 [11028.286786] [] inet_ioctl+0x88/0xa0 [11028.292633] [] sock_ioctl+0x7a/0x280 [11028.298576] [] vfs_ioctl+0x22/0xa0 [11028.304326] [] ? unmap_region+0x110/0x130 [11028.310756] [] do_vfs_ioctl+0x84/0x580 [11028.316897] [] sys_ioctl+0x81/0xa0 and 11028.017533] [] ? perf_event_task_sched_out+0x33/0x80 [11028.025030] [] ? apic_timer_interrupt+0xe/0x20 [11028.031945] [] __mutex_lock_slowpath+0x13e/0x180 [11028.039053] [] mutex_lock+0x2b/0x50 [11028.044910] [] __ipoib_ib_dev_flush+0x37/0x210 [ib_ipoib] [11028.052894] [] ? ipoib_ib_dev_flush_light+0x0/0x20 [ib_ipoib] [11028.061363] [] ipoib_ib_dev_flush_light+0x17/0x20 [ib_ipoib] [11028.069738] [] worker_thread+0x170/0x2a0 [11028.076068] [] ? autoremove_wake_function+0x0/0x40 [11028.083374] [] ? worker_thread+0x0/0x2a0 [11028.089709] [] kthread+0x96/0xa0 [11028.095266] [] child_rip+0xa/0x20 [11028.100921] [] ? kthread+0x0/0xa0 [11028.106573] [] ? child_rip+0x0/0x20 [11028.112423] INFO: task ifconfig:23640 blocked for more than 120 seconds. Signed-off-by: Erez Shitrit Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- drivers/infiniband/ulp/ipoib/ipoib_vlan.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'drivers/infiniband/ulp/ipoib/ipoib_vlan.c') diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index 8292554bccb5..9fad7b5ac8b9 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -140,7 +140,7 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) if (!rtnl_trylock()) return restart_syscall(); - mutex_lock(&ppriv->vlan_mutex); + down_write(&ppriv->vlan_rwsem); /* * First ensure this isn't a duplicate. We check the parent device and @@ -163,7 +163,7 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) result = __ipoib_vlan_add(ppriv, priv, pkey, IPOIB_LEGACY_CHILD); out: - mutex_unlock(&ppriv->vlan_mutex); + up_write(&ppriv->vlan_rwsem); if (result) free_netdev(priv->dev); @@ -185,7 +185,8 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey) if (!rtnl_trylock()) return restart_syscall(); - mutex_lock(&ppriv->vlan_mutex); + + down_write(&ppriv->vlan_rwsem); list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) { if (priv->pkey == pkey && priv->child_type == IPOIB_LEGACY_CHILD) { @@ -195,7 +196,8 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey) break; } } - mutex_unlock(&ppriv->vlan_mutex); + up_write(&ppriv->vlan_rwsem); + rtnl_unlock(); if (dev) { -- cgit v1.2.3-59-g8ed1b